Support exaone4 model

[zhaohb]

Just for EXAONE-4.0-1.2B

ticket : 175853

What does this PR do?

Conversion cmd-line for LGAI-EXAONE/EXAONE-4.0-1.2B:

optimum-cli export openvino -m  LGAI-EXAONE/EXAONE-4.0-1.2B EXAONE-4.0-1.2B

Inference of LGAI-EXAONE/EXAONE-4.0-1.2B using OpenVINO backend:

import torch
from transformers import AutoTokenizer
from optimum.intel.openvino import OVModelForCausalLM

model_dir="LGAI-EXAONE/EXAONE-4.0-1.2B"

tokenizer = AutoTokenizer.from_pretrained(model_dir)
model = OVModelForCausalLM.from_pretrained(model_dir)

prompt = "What is the capital of France?"

messages = [
    {"role": "user", "content": prompt}
]
input_ids = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=True,
    return_tensors="pt"
)

# Run inference
output_ids = model.generate(input_ids, max_new_tokens=10)
output_text = tokenizer.decode(output_ids[0])

print(output_text)

Before submitting

• [N/A] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you make sure to update the documentation with your changes?
• Did you write any new necessary tests?

[rkazants]

Please provide tests and JIRA ticket.

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[zhaohb]

Please provide tests and JIRA ticket.

Hi, I had add JITA ticket and tests.
Thank you very much.

[rkazants]

OVModelForSequenceClassification is not validated. I see that this task is not validated in precommit.
The same problem is for feature-extraction.

[rkazants]

@zhaohb, please provide PR description in a format as here: #1354
Example:

[zhaohb]

@zhaohb, please provide PR description in a format as here: #1354 Example:

Done, thanks.

[rkazants]

Please add test cases here https://github.com/huggingface/optimum-intel/blob/main/tests/openvino/test_quantization.py